Training in progress, step 100

README.md

@@ -2,11 +2,12 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 base_model: mistralai/Mistral-7B-v0.1
 model-index:
 - name: zephyr-7b-sft-qlora
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
 
 ## Model description
 

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "q_proj",
     "down_proj",
-    "gate_proj",
     "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

runs/Apr14_00-46-18_g3023/events.out.tfevents.1713080903.g3023.43510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda7c25ba7b78ec2b9eaa6e6f3b364ff822b8eb0f84f6f6d8b3f87c0a1e1e48f
+size 7686

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142a14809e285e427e561c3b563130821d0cd6c4f7c809c3cdfa0bbd0db3409d
+oid sha256:e9072246606f256490c0ed9a8396d3efa810970ac671473c4e0dcfb4e74a474d
 size 4792